MIT researchers have developed a type of neural network that learns on the job, not just during its training phase. These flexible algorithms, dubbed “liquid” networks, change their underlying equations to continuously adapt to new data inputs. The advance could aid decision making based on data streams that change over time, including those involved in medical diagnosis and autonomous driving.

MIT researchers have developed a way for deep learning neural networks to rapidly estimate confidence levels in their output. The advance could enhance safety and efficiency in AI-assisted decision making.

In a new paper, a team led by MIT computer scientists trained a neural network to learn NASCAR-style driving maneuvers purely from looking at a sequence of images taken from a two-person racing game. The network begins without knowing anything about cars, roads, or driving - and yet ultimately becomes able to do complex moves like overtaking an opponent on a turn and even forcing other cars off the road. 

One of the biggest challenges in computing is handling the onslaught of information while still being able to efficiently store and process it. A team from MIT CSAIL believe that the answer rests with something called “instance-optimized systems.”

CSAIL Alliances Startup Connect member Composable Analytics teams up with CheckAlt to incorporate cognitive automation to payment data capture.